feat(embedding): add WeMM-Embedding support - #5439
Merged
qinxuye merged 3 commits intoAug 29, 2026
Merged
Conversation
Support multimodal text, image, video, and interleaved inputs through sentence-transformers and vLLM with Hugging Face and ModelScope sources.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request adds support for the WeMM-Embedding model family (2B, 4B, and 9B) in Xinference, enabling multimodal inputs (text, image, and video) across both the sentence_transformers and vllm engines. It updates API schemas, restful clients, and core embedding logic to support structured multimodal inputs, and includes a PyAV-based video reader fallback. The review feedback correctly points out that the specified dependency versions for sentence-transformers (>=5.7.0) and transformers (>=5.2.0) do not exist on PyPI and must be updated to valid, existing versions.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Support multimodal text, image, video, and interleaved inputs through sentence-transformers and vLLM with Hugging Face and ModelScope sources.
Summary
Add built-in support for Tencent's multimodal WeMM-Embedding model family:
WeMM-Embedding-2BWeMM-Embedding-4BWeMM-Embedding-9BModels are available from:
mainmasterSupported embedding engines are intentionally limited to existing Xinference backends:
sentence_transformersvllmModel Metadata